Apple's accidental moat: How the "AI Loser" may end up winning

Re:Apple's accidental moat: How the "AI Loser" may end up wi... by blitzar on Monday April 13, 2026 @02:01AM (#47748160)

> it’s not great at using all tools

Glad it wasnt just me - i was impressed with the quality of Gemma4 - it just couldnt write the changes to file 9/10 times when using it with opencode

[ Parent | on HN ]

Re:Apple's accidental moat: How the "AI Loser" may end up wi... by seaal on Monday April 13, 2026 @02:06AM (#47748196)

There was an update to tool calling 3 days ago. I haven't tested it myself but hope it helps.

[ Parent | on HN ]

Re:Apple's accidental moat: How the "AI Loser" may end up wi... by sroussey on Monday April 13, 2026 @02:57AM (#47748605)

Hmm.. is there an updated onnx?

[ Parent | on HN ]

Re:Apple's accidental moat: How the "AI Loser" may end up wi... by blitzar on Monday April 13, 2026 @08:15AM (#47750905)

Wow, that is so much better! I didnt exactly test it extensively but my issues are gone.

[ Parent | on HN ]

Re:Apple's accidental moat: How the "AI Loser" may end up wi... by erichocean on Monday April 13, 2026 @03:54AM (#47749057)

> it just couldnt write the changes to file 9/10 times when using it with opencode

You might want to give this a try, it dramatically improves Edit tool accuracy without changing the model: https://blog.can.ac/2026/02/12/the-harness-problem/

[ Parent | on HN ]